High-Performance Scaphoid Fracture Recognition via Effectiveness Assessment of Artificial Neural Networks
Image recognition through the use of deep learning (DL) techniques has recently become a hot topic in many fields. Especially for bioimage informatics, DL-based image recognition has been successfully used in several applications, such as cancer and fracture detection. However, few previous studies...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-09-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/18/8485 |
id |
doaj-419fbeed026b4e8081f45d8bbd32fc46 |
---|---|
record_format |
Article |
spelling |
doaj-419fbeed026b4e8081f45d8bbd32fc462021-09-25T23:40:09ZengMDPI AGApplied Sciences2076-34172021-09-01118485848510.3390/app11188485High-Performance Scaphoid Fracture Recognition via Effectiveness Assessment of Artificial Neural NetworksYu-Cheng Tung0Ja-Hwung Su1Yi-Wen Liao2Ching-Di Chang3Yu-Fan Cheng4Wan-Ching Chang5Bo-Hong Chen6Department of Diagnostic Radiology, Kaohsiung Chang Gung Memorial Hospital, Chang Gung University College of Medicine, Kaohsiung 83347, TaiwanDepartment of Computer Science and Information Engineering, National University of Kaohsiung, Kaohsiung 83347, TaiwanDepartment of Information Management, Cheng Shiu University, Kaohsiung 83347, TaiwanDepartment of Diagnostic Radiology, Kaohsiung Chang Gung Memorial Hospital, Chang Gung University College of Medicine, Kaohsiung 83347, TaiwanDepartment of Diagnostic Radiology, Kaohsiung Chang Gung Memorial Hospital, Chang Gung University College of Medicine, Kaohsiung 83347, TaiwanDepartment of Diagnostic Radiology, Kaohsiung Chang Gung Memorial Hospital, Chang Gung University College of Medicine, Kaohsiung 83347, TaiwanDepartment of Information Management, Cheng Shiu University, Kaohsiung 83347, TaiwanImage recognition through the use of deep learning (DL) techniques has recently become a hot topic in many fields. Especially for bioimage informatics, DL-based image recognition has been successfully used in several applications, such as cancer and fracture detection. However, few previous studies have focused on detecting scaphoid fractures, and the related effectiveness is also not significant. Aimed at this issue, in this paper, we present a two-stage method for scaphoid fracture recognition by conducting an effectiveness analysis of numerous state-of-the-art artificial neural networks. In the first stage, the scaphoid bone is extracted from the radiograph using object detection techniques. Based on the object extracted, several convolutional neural networks (CNNs), with or without transfer learning, are utilized to recognize the segmented object. Finally, the analytical details on a real data set are given, in terms of various evaluation metrics, including sensitivity, specificity, precision, F1-score, area under the receiver operating curve (AUC), kappa, and accuracy. The experimental results reveal that the CNNs with transfer learning are more effective than those without transfer learning. Moreover, DenseNet201 and ResNet101 are found to be more promising than the other methods, on average. According to the experimental results, DenseNet201 and ResNet101 can be recommended as considerable solutions for scaphoid fracture detection within a bioimage diagnostic system.https://www.mdpi.com/2076-3417/11/18/8485scaphoid fractureimage recognitiondeep learningartificial intelligenceconvolutional neural networks |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yu-Cheng Tung Ja-Hwung Su Yi-Wen Liao Ching-Di Chang Yu-Fan Cheng Wan-Ching Chang Bo-Hong Chen |
spellingShingle |
Yu-Cheng Tung Ja-Hwung Su Yi-Wen Liao Ching-Di Chang Yu-Fan Cheng Wan-Ching Chang Bo-Hong Chen High-Performance Scaphoid Fracture Recognition via Effectiveness Assessment of Artificial Neural Networks Applied Sciences scaphoid fracture image recognition deep learning artificial intelligence convolutional neural networks |
author_facet |
Yu-Cheng Tung Ja-Hwung Su Yi-Wen Liao Ching-Di Chang Yu-Fan Cheng Wan-Ching Chang Bo-Hong Chen |
author_sort |
Yu-Cheng Tung |
title |
High-Performance Scaphoid Fracture Recognition via Effectiveness Assessment of Artificial Neural Networks |
title_short |
High-Performance Scaphoid Fracture Recognition via Effectiveness Assessment of Artificial Neural Networks |
title_full |
High-Performance Scaphoid Fracture Recognition via Effectiveness Assessment of Artificial Neural Networks |
title_fullStr |
High-Performance Scaphoid Fracture Recognition via Effectiveness Assessment of Artificial Neural Networks |
title_full_unstemmed |
High-Performance Scaphoid Fracture Recognition via Effectiveness Assessment of Artificial Neural Networks |
title_sort |
high-performance scaphoid fracture recognition via effectiveness assessment of artificial neural networks |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2021-09-01 |
description |
Image recognition through the use of deep learning (DL) techniques has recently become a hot topic in many fields. Especially for bioimage informatics, DL-based image recognition has been successfully used in several applications, such as cancer and fracture detection. However, few previous studies have focused on detecting scaphoid fractures, and the related effectiveness is also not significant. Aimed at this issue, in this paper, we present a two-stage method for scaphoid fracture recognition by conducting an effectiveness analysis of numerous state-of-the-art artificial neural networks. In the first stage, the scaphoid bone is extracted from the radiograph using object detection techniques. Based on the object extracted, several convolutional neural networks (CNNs), with or without transfer learning, are utilized to recognize the segmented object. Finally, the analytical details on a real data set are given, in terms of various evaluation metrics, including sensitivity, specificity, precision, F1-score, area under the receiver operating curve (AUC), kappa, and accuracy. The experimental results reveal that the CNNs with transfer learning are more effective than those without transfer learning. Moreover, DenseNet201 and ResNet101 are found to be more promising than the other methods, on average. According to the experimental results, DenseNet201 and ResNet101 can be recommended as considerable solutions for scaphoid fracture detection within a bioimage diagnostic system. |
topic |
scaphoid fracture image recognition deep learning artificial intelligence convolutional neural networks |
url |
https://www.mdpi.com/2076-3417/11/18/8485 |
work_keys_str_mv |
AT yuchengtung highperformancescaphoidfracturerecognitionviaeffectivenessassessmentofartificialneuralnetworks AT jahwungsu highperformancescaphoidfracturerecognitionviaeffectivenessassessmentofartificialneuralnetworks AT yiwenliao highperformancescaphoidfracturerecognitionviaeffectivenessassessmentofartificialneuralnetworks AT chingdichang highperformancescaphoidfracturerecognitionviaeffectivenessassessmentofartificialneuralnetworks AT yufancheng highperformancescaphoidfracturerecognitionviaeffectivenessassessmentofartificialneuralnetworks AT wanchingchang highperformancescaphoidfracturerecognitionviaeffectivenessassessmentofartificialneuralnetworks AT bohongchen highperformancescaphoidfracturerecognitionviaeffectivenessassessmentofartificialneuralnetworks |
_version_ |
1717368298752966656 |